{"data":{"id":"0fd60abd-3dab-4e01-a1b5-037a91fb65f0","title":"Detecting and Mitigating Query-Based System Prompt Leakage Attacks","summary":"Researchers present AdvGuard, a model-agnostic framework that detects and mitigates system prompt leakage by modeling cross-query relationships with a bounded semantic interaction graph and a GCN classifier. In mixed-query tests it improves recall by up to 36% over the strongest baseline at a false positive rate of at most 3.4%. Integrated into the adaptive PLeak and LeakAgent attack loops, it limits exact-match leakage to 0.00-0.01 across evaluated victim models.","solution":"AdvGuard, a model-agnostic framework that detects and mitigates system prompt leakage, with a lightweight prompt-level detector that provides protection before sufficient interaction history accumulates.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.36295v1","publishedAt":"2026-10-26T21:23:10.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["data_extraction"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-26T21:23:10.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}